Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.1837. Min Act: -0.1700

Data Index: 4426503 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0989. Min Act: -0.1700

Data Index: 352003 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0899. Min Act: -0.1700

Data Index: 1638916 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0674. Min Act: -0.1700

Data Index: 4132605 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0624. Min Act: -0.1700

Data Index: 6195247 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0523. Min Act: -0.1700

Data Index: 881415 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0616. Min Act: -0.1700

Data Index: 8004436 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0380. Min Act: -0.1700

Data Index: 3093199 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0421. Min Act: -0.1700

Data Index: 8016997 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0347. Min Act: -0.1700

Data Index: 1092473 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0189. Min Act: -0.1700

Data Index: 6684816 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0038. Min Act: -0.1700

Data Index: 5825346 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0077. Min Act: -0.1700

Data Index: 4426507 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.1837. Min Range: -3.1837

Max Act: 2.9903. Min Act: -0.1700

Data Index: 6069665 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1837. Min Range: -3.1837

Max Act: 2.9936. Min Act: -0.1700

Data Index: 4218159 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0004. Min Act: -0.1700

Data Index: 7030603 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.1837. Min Range: -3.1837

Max Act: 2.9912. Min Act: -0.1700

Data Index: 3122550 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0061. Min Act: -0.1700

Data Index: 1250909 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1837. Min Range: -3.1837

Max Act: 3.0061. Min Act: -0.1700

Data Index: 8583041 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1837. Min Range: -3.1837

Max Act: 2.9988. Min Act: -0.1700

Data Index: 2195127 (Open Web Text)

Max Activating Token Index: 6